© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 103019
    Prev
    Next
    INDEX
    Explanations

    <|message|>

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dacă
    -0.08
     such
    -0.08
     såsom
    -0.07
     △
    -0.07
     stip
    -0.07
     solche
    -0.07
     infiltr
    -0.07
     collar
    -0.07
     estip
    -0.07
     Jika
    -0.07
    POSITIVE LOGITS
    国产精品
    0.10
    一区二区三区
    0.10
     جاه
    0.10
    Actually
    0.10
    精品国产
    0.10
    无码
    0.10
    高清免费
    0.10
    电影在线观看
    0.10
    xtəlif
    0.10
     өөр
    0.10
    Activations Density 0.003%

    No Known Activations